Upcoming
Stop Reviewing AI Outputs. Start Engineering Them
How to design an AI workflow fit for real safety work.
Talks and papers
On AI-assisted hazard analysis, cybersecurity in safety cases and AI adoption in safety-critical engineering.
How to Make the Most of AI: A Workshop for Safety Engineers
Prompt and context engineering for safety engineers: practitioner talks in the morning, hands-on workshops in the afternoon. With Paul Hampton, Rudi Hennessy and Alan Simpson.
Can AI deliver a credible HAZOP?
With Lucas Domingues, on where AI adds value in safety-critical engineering and where the hype outruns it.
AI-assisted HAZOP: Can prompt engineering deliver a credible HAZOP assessment?
An LLM tested against a real HAZOP for a deployable water treatment system. It worked like a methodical junior engineer, and its errors were the reviewable kind. Lead author, with Thomas Wilkinson, Mathew Wylie and Luke Hankins.
Merging Human Expertise with AI for Better Safety Management
The SCSC keynote, given again by invitation for IChemE.
Merging Human Expertise with AI for Better Safety Management
How large language models can support and strengthen established safety engineering practice, with engineers keeping the judgement.
Bridging risk paradigms from cyber threats to safety impacts: a new assessment process
Effectiveness of Controls: a method for bringing cybersecurity risk into safety cases to support ALARP arguments, now applied across multiple platforms. Lead author, with Mathew Wylie and Neil Stiff.
Speaking on AI adoption in regulated industries, for conferences, seminars, podcasts and in-house sessions.